agentleFS
Sign inStart free
ahmedsakriahmedsakri/youtube-agent-pro/skills/yt-script/SKILL.md

yt-script

Skill1 starsChanged 35 days agoMITView on GitHub

Write a YouTube video script from a raw idea - hook options off 21 formulas, scored, then the full spoken script with the retention beats marked. Use whenever the user wants a video script, a hook, an opening line, "what should I say", "write my next video", or is about to record and does not have the first fifteen seconds yet.

6 other projects use a version of this, 4 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 1 is common, 2 are distinctive, and 2 are very specific to this project.

  • 1

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the shared operating guide for profile lookup, helper paths, capability limits, and cross-skill routing before using this workflow.

    line 13
  2. Very specific:

    Use the creator's supplied voice profile or context, then a local ~/.claude/youtube/voice.md if available, following the operating guide.

    line 28
  3. Common:

    Never invent a number, a result or a source.

    line 31
  4. Very specific:

    Hook: Write FIVE against the 21 formulas, run them through hookscore.py, keep the strongest options, and report actual scores if run.

    line 40
  5. Distinctive:

    Keep setup brief and avoid delaying the promised content with an unrelated intro or subscribe pitch.

    line 44

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

yt-script

Read the shared operating guide for profile lookup, helper paths, capability limits, and cross-skill routing before using this workflow.

One idea into a script somebody finishes.

hookscore.py scores candidate hooks against the accompanying formula library. Use it when execution is available; its scores are writing heuristics, not predictions of viewer retention.

python3 "$YT_SKILL_DIR/hookscore.py" hooks.txt              # rank your hook options
python3 "$YT_SKILL_DIR/hookscore.py" --hook "one line"      # score a single one

Before you write

  1. Use the creator's supplied voice profile or context, then a local ~/.claude/youtube/voice.md if available, following the operating guide. If absent, draft in a clear voice using the stated audience and format; do not make voice-profile setup a prerequisite.
  2. Never invent a number, a result or a source. If a figure would strengthen it and you do not have one, ask for it or write the line without it.

The shape

The opening must earn attention. Confirm the title's promise, open a meaningful question, and show a reason to expect the payoff. The times below suit a longer video; for Shorts, establish context in the first seconds and scale every beat to the requested runtime.

  1. Hook. Write FIVE against the 21 formulas, run them through hookscore.py, keep the strongest options, and report actual scores if run. If the user requests one final hook, select it and continue into the full script.
  2. The turn (0:15-0:45). Say what the video is going to do, in one sentence, and start doing it. Keep setup brief and avoid delaying the promised content with an unrelated intro or subscribe pitch.
  3. The body. One idea per beat. Mark each beat with what is ON SCREEN, not just what is said - a talking head with nothing to look at is a podcast.
  4. The payoff. Deliver the thing the hook promised, explicitly, and say that you are delivering it: "that is the prompt, it is in the description".
  5. The close. One ask. Not three.

What to hand back

  • the two best hooks with their scored panels
  • the script, beat by beat, with [ON SCREEN: ...] on every beat
  • a runtime estimate from the spoken words (150 words/minute is a starting assumption), with pauses, visual beats, and the creator's actual delivery speed accounted for
  • one line naming which formula the winning hook used and why it fits this idea

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free